import xarray as xr

# Read
ds = xr.open_dataset('data.nc')

# Access data
temp = ds['temperature']         # DataArray
values = temp.values             # numpy array
df = ds.to_dataframe()           # pandas DataFrame

# Structure info
print(ds)                        # Overview
print(ds.dims)                   # Dimensions
print(ds.data_vars)              # Variables

# Write
ds.to_netcdf('output.nc')

# By coordinate value
temp_jan = ds['temperature'].sel(time='2020-01-15')
temp_region = ds['temperature'].sel(lat=slice(-30, 30), lon=slice(-60, 60))

# Nearest value
temp_point = ds['temperature'].sel(lat=35.5, lon=-120.3, method='nearest')

# By index
temp_first = ds['temperature'].isel(time=0)

temp = ds['temperature']
temp_mean_time = temp.mean(dim='time')           # Spatial map
temp_mean_space = temp.mean(dim=['lat', 'lon'])  # Time series

# Area-weighted mean
import numpy as np
weights = np.cos(np.deg2rad(ds.lat))
temp_weighted = temp.weighted(weights).mean(dim=['lat', 'lon'])

temp = ds['temperature']

# Temporal aggregations
monthly_mean = temp.groupby('time.month').mean()
annual_mean = temp.groupby('time.year').mean()

# Climatology and anomalies
climatology = temp.groupby('time.month').mean('time')
anomalies = temp.groupby('time.month') - climatology

# Resample time series
monthly = temp.resample(time='1M').mean()
rolling_30d = temp.rolling(time=30, center=True).mean()

import numpy as np
import pandas as pd

times = pd.date_range('2020-01-01', periods=365, freq='D')
lats = np.linspace(-90, 90, 180)
lons = np.linspace(-180, 180, 360)

da = xr.DataArray(
    data=np.random.randn(365, 180, 360),
    dims=['time', 'lat', 'lon'],
    coords={'time': times, 'lat': lats, 'lon': lons},
    attrs={'units': 'degC', 'long_name': 'Temperature'}
)

ds = xr.Dataset({'temperature': da})
ds.to_netcdf('output.nc')

temp_warm = temp.where(temp > 20)                 # Mask by condition
temp_clipped = temp.where(temp > 0, 0)            # Replace negative with 0

tropics = (ds.lat > -23.5) & (ds.lat < 23.5)
temp_tropics = temp.where(tropics, drop=True)    # Mask by coordinate

# Open with chunking (lazy loading)
ds = xr.open_dataset('large_file.nc', chunks={'time': 100})
ds = xr.open_mfdataset('data_*.nc', chunks='auto')

# Operations are lazy until .compute()
result = ds['temperature'].mean(dim='time').compute()